PENet: A Joint Panoptic Edge Detection Network
This work addresses the need for efficient scene understanding in robotic systems, though it appears incremental as it extends existing semantic edge detection to include instance-aware segmentation.
The authors tackled the problem of creating compact scene understanding representations for robotics by proposing PENet, a joint network that combines semantic edge detection and instance-level perception into panoptic edge segmentation, achieving effectiveness validated on the Cityscapes dataset.
In recent years, compact and efficient scene understanding representations have gained popularity in increasing situational awareness and autonomy of robotic systems. In this work, we illustrate the concept of a panoptic edge segmentation and propose PENet, a novel detection network called that combines semantic edge detection and instance-level perception into a compact panoptic edge representation. This is obtained through a joint network by multi-task learning that concurrently predicts semantic edges, instance centers and offset flow map without bounding box predictions exploiting the cross-task correlations among the tasks. The proposed approach allows extending semantic edge detection to panoptic edge detection which encapsulates both category-aware and instance-aware segmentation. We validate the proposed panoptic edge segmentation method and demonstrate its effectiveness on the real-world Cityscapes dataset.